{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RH2YDBGQQ2KXPYQPV6YGB5525R","short_pith_number":"pith:RH2YDBGQ","schema_version":"1.0","canonical_sha256":"89f58184d0869577e20fafb060f7baec4c65883e327bf82b073023280c370ea0","source":{"kind":"arxiv","id":"2410.00324","version":6},"attestation_state":"computed","paper":{"title":"Vision Language Models See What You Want but not What You See","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dezhi Luo, Haiyun Lyu, Haoran Sun, Hokin Deng, Qingying Gao, Yijiang Li","submitted_at":"2024-10-01T01:52:01Z","abstract_excerpt":"Knowing others' intentions and taking others' perspectives are two core components of human intelligence that are considered to be instantiations of theory-of-mind. Infiltrating machines with these abilities is an important step towards building human-level artificial intelligence. Here, to investigate intentionality understanding and level-2 perspective-taking in Vision Language Models (VLMs), we constructed the IntentBench and PerspectBench, which together contains over 300 cognitive experiments grounded in real-world scenarios and classic cognitive tasks. We found VLMs achieving high perfor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.00324","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-01T01:52:01Z","cross_cats_sorted":[],"title_canon_sha256":"a173aa3e481e5af3a3536172ed1643bf5c672c6e5423d2533561df80004d32c2","abstract_canon_sha256":"28cef0ea3f7613962e52f8b939552bff299456a885b038a494ffd2e643b5cbba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:15.078177Z","signature_b64":"Z7xxR59O9DXQHxrrZl5ZZUJaWpQBTAun24uVm+RkhQutSLFX5DCqtgcyRUoqpiJoM6Ou3pJ0yIf8Opb5H4l0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f58184d0869577e20fafb060f7baec4c65883e327bf82b073023280c370ea0","last_reissued_at":"2026-07-05T11:52:15.077734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:15.077734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Language Models See What You Want but not What You See","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dezhi Luo, Haiyun Lyu, Haoran Sun, Hokin Deng, Qingying Gao, Yijiang Li","submitted_at":"2024-10-01T01:52:01Z","abstract_excerpt":"Knowing others' intentions and taking others' perspectives are two core components of human intelligence that are considered to be instantiations of theory-of-mind. Infiltrating machines with these abilities is an important step towards building human-level artificial intelligence. Here, to investigate intentionality understanding and level-2 perspective-taking in Vision Language Models (VLMs), we constructed the IntentBench and PerspectBench, which together contains over 300 cognitive experiments grounded in real-world scenarios and classic cognitive tasks. We found VLMs achieving high perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00324","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.00324/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.00324","created_at":"2026-07-05T11:52:15.077791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00324v6","created_at":"2026-07-05T11:52:15.077791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00324","created_at":"2026-07-05T11:52:15.077791+00:00"},{"alias_kind":"pith_short_12","alias_value":"RH2YDBGQQ2KX","created_at":"2026-07-05T11:52:15.077791+00:00"},{"alias_kind":"pith_short_16","alias_value":"RH2YDBGQQ2KXPYQP","created_at":"2026-07-05T11:52:15.077791+00:00"},{"alias_kind":"pith_short_8","alias_value":"RH2YDBGQ","created_at":"2026-07-05T11:52:15.077791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12413","citing_title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12413","citing_title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12413","citing_title":"Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R","json":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R.json","graph_json":"https://pith.science/api/pith-number/RH2YDBGQQ2KXPYQPV6YGB5525R/graph.json","events_json":"https://pith.science/api/pith-number/RH2YDBGQQ2KXPYQPV6YGB5525R/events.json","paper":"https://pith.science/paper/RH2YDBGQ"},"agent_actions":{"view_html":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R","download_json":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R.json","view_paper":"https://pith.science/paper/RH2YDBGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00324&json=true","fetch_graph":"https://pith.science/api/pith-number/RH2YDBGQQ2KXPYQPV6YGB5525R/graph.json","fetch_events":"https://pith.science/api/pith-number/RH2YDBGQQ2KXPYQPV6YGB5525R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R/action/storage_attestation","attest_author":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R/action/author_attestation","sign_citation":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R/action/citation_signature","submit_replication":"https://pith.science/pith/RH2YDBGQQ2KXPYQPV6YGB5525R/action/replication_record"}},"created_at":"2026-07-05T11:52:15.077791+00:00","updated_at":"2026-07-05T11:52:15.077791+00:00"}